josephmayo/Qwopus-9B-Unfettered
9B • Updated • 320 • 19
josephmayo
josephmayo
AI & ML interests
ai safety /red teaming, unfettering, guardrails & fine tuning
Recent Activity
reacted to danielhanchen's post with 🔥 2 days ago
We collaborated with NVIDIA to teach you how we made LLM training ~25% faster! 🚀
Learn how 3 optimizations help your home GPU train models faster:
1. Packed-sequence metadata caching
2. Double-buffered checkpoint reloads
3. Faster MoE routing
Guide: https://unsloth.ai/blog/nvidia-collab
GitHub: https://github.com/unslothai/unsloth new activity 4 days ago
Zyphra/ZAYA1-8B:quantized and RSA liked a model 5 days ago
Zyphra/ZAYA1-8BOrganizations
None yet